ramdhanfirdaus commited on
Commit
954674f
1 Parent(s): a1f2868

Training in progress, step 2000, checkpoint

Browse files
last-checkpoint/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab75aade6b4b862185eff4e74cf3992f0a79d47c9a455812179b06c54a17786a
3
  size 50349441
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6048585c2f8e2bb3c47daca9108b59a276824ef2ef40c8fb8785552f8267207
3
  size 50349441
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdd9c2f532a6939f31c40191a87658416212c0c414f85ae99b07e669c6405911
3
  size 100691721
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:441b44686e1d19df37d3eee80ad380030d35dff5f7f7e7d1b75e7a9487a54fe9
3
  size 100691721
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2cb8bf46e727b10f6454296d435cc1e136b3df586aaf0e24b91f6eb44c61503
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79442ccc7dfdbf1674cc819a92eae75e113128f4ead630f5201f2c5440168541
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.48880934715271,
3
- "best_model_checkpoint": "./outputs/checkpoint-1900",
4
- "epoch": 1.3846994535519126,
5
  "eval_steps": 100,
6
- "global_step": 1900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -273,13 +273,27 @@
273
  "eval_samples_per_second": 46.95,
274
  "eval_steps_per_second": 5.874,
275
  "step": 1900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
276
  }
277
  ],
278
  "logging_steps": 100,
279
  "max_steps": 4116,
280
  "num_train_epochs": 3,
281
  "save_steps": 100,
282
- "total_flos": 1.1326073560441651e+17,
283
  "trial_name": null,
284
  "trial_params": null
285
  }
 
1
  {
2
+ "best_metric": 1.4694921970367432,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2000",
4
+ "epoch": 1.4575591985428051,
5
  "eval_steps": 100,
6
+ "global_step": 2000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
273
  "eval_samples_per_second": 46.95,
274
  "eval_steps_per_second": 5.874,
275
  "step": 1900
276
+ },
277
+ {
278
+ "epoch": 1.46,
279
+ "learning_rate": 0.0002,
280
+ "loss": 1.4621,
281
+ "step": 2000
282
+ },
283
+ {
284
+ "epoch": 1.46,
285
+ "eval_loss": 1.4694921970367432,
286
+ "eval_runtime": 133.7845,
287
+ "eval_samples_per_second": 46.896,
288
+ "eval_steps_per_second": 5.868,
289
+ "step": 2000
290
  }
291
  ],
292
  "logging_steps": 100,
293
  "max_steps": 4116,
294
  "num_train_epochs": 3,
295
  "save_steps": 100,
296
+ "total_flos": 1.1922500576224051e+17,
297
  "trial_name": null,
298
  "trial_params": null
299
  }